爬虫大作业

1.选一个自己感兴趣的主题或网站。(所有同学不能雷同)

2.用python 编写爬虫程序，从网络上爬取相关主题的数据。

3.对爬了的数据进行文本分析，生成词云。

4.对文本分析结果进行解释说明。

5.写一篇完整的博客，描述上述实现过程、遇到的问题及解决办法、数据分析思想及结论。

6.最后提交爬取的全部数据、爬虫及数据分析源代码。

import requests
from bs4 import BeautifulSoup
import jieba.analyse
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,ImageColorGenerator


url = "https://item.btime.com/36soaocmq3b884qcrm1phg2upnh?from=haozcxw"
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')


title = soup.select('.title')[0].text
content = soup.select('.content-text')[0].text

f = open('conten.txt', 'a', encoding='utf-8')
f.write(content)
f.close()

strl = '''，。、‘’ '''
for i in strl:
    ls = content.replace(i," ")
    print(ls)


lyric= ''
f=open('conten.txt','r', encoding='utf-8')
for i in f:
    lyric+=f.read()


result=jieba.analyse.textrank(lyric,topK=50,withWeight=True)
keywords = dict()
for i in result:
    keywords[i[0]]=i[1]
print(keywords)

image= Image.open('11c1e099855d27b7cf3e174e25e501cc_t015f10572a0691eaa8.jpg')
graph = np.array(image)
wc = WordCloud(font_path='./fonts/simhei.ttf',background_color='White',max_words=50,mask=graph)
wc.generate_from_frequencies(keywords)
image_color = ImageColorGenerator(graph)
plt.imshow(wc)
plt.imshow(wc.recolor(color_func=image_color))
plt.axis("off")
plt.show()
wc.to_file('d.jpg')